Alternatives and similar repositories for modelcomponents

Users that are interested in modelcomponents are comparing it to the libraries listed below

• multimodal-interpretability / maia
  Official implementation of MAIA, A Multimodal Automated Interpretability Agent
  ☆102Updated 3 months ago
• g-luo / vlm_cross_modal_reps
  Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025
  ☆32Updated 9 months ago
• AmeenAli / HiddenMambaAttn
  Official PyTorch Implementation of "The Hidden Attention of Mamba Models"
  ☆231Updated 3 months ago
• goombalab / phi-mamba
  Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…
  ☆119Updated last year
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆64Updated last year
• ChenWu98 / algorithmic-creativity
  [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
  ☆84Updated 8 months ago
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆119Updated 2 months ago
• katiekang1998 / reasoning_generalization
  ☆33Updated last year
• jonhue / activeft
  PyTorch library for Active Fine-Tuning
  ☆96Updated 4 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆83Updated last year
• oripress / EntropyEnigma
  Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"
  ☆55Updated last year
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆135Updated 3 months ago
• EvolvingLMMs-Lab / multimodal-sae
  [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.
  ☆175Updated 4 months ago
• uclaml / MoE
  Towards Understanding the Mixture-of-Experts Layer in Deep Learning
  ☆35Updated 2 years ago
• RobertCsordas / moeut
  ☆91Updated last year
• lucidrains / coconut-pytorch
  Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch
  ☆182Updated 7 months ago
• wang-kee / LiNeS
  Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"
  ☆31Updated last year
• Weixin-Liang / Mixture-of-Mamba
  ☆50Updated last year
• prateeky2806 / ties-merging
  ☆208Updated 2 years ago
• Luckfort / CD
  [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
  ☆82Updated last year
• ycjing / Awesome-Model-Merging
  A curated list of Model Merging methods.
  ☆96Updated 2 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆241Updated last week
• jxiw / MambaInLlama
  [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models
  ☆237Updated 3 months ago
• peterljq / Parsimonious-Concept-Engineering
  PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆42Updated 3 weeks ago
• pengzhangzhi / Awesome-Mamba
  Awesome list of papers that extend Mamba to various applications.
  ☆138Updated 7 months ago
• ml-jku / EVA
  One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation
  ☆46Updated 3 months ago
• abdelwahed / OT_for_big_data
  Optimal Transport in the Big Data Era
  ☆116Updated last year
• locuslab / massive-activations
  Code accompanying the paper "Massive Activations in Large Language Models"
  ☆195Updated last year
• kyegomez / Mixture-of-Depths
  Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆114Updated last week
• MadryLab / DsDm
  ☆51Updated 2 years ago